One API for every model
Access 20+ open-source and frontier models through one API. All models support streaming, tool calls, and structured outputs.
Open Source
High-performance open-weight models
| Model | Input / MTok | Output / MTok | Context |
|---|---|---|---|
| Llama 3.1 405B | $3.00 | $3.00 | 128K |
| Llama 3.1 70B | $0.35 | $0.40 | 128K |
| Llama 3.1 8B | $0.05 | $0.05 | 128K |
| Mistral 7B | $0.05 | $0.05 | 32K |
| Mixtral 8x7B | $0.24 | $0.24 | 32K |
Frontier
Latest closed-source models
| Model | Input / MTok | Output / MTok | Context |
|---|---|---|---|
| GPT-4o | $2.50 | $10.00 | 128K |
| GPT-4o mini | $0.15 | $0.60 | 128K |
| Claude 3.7 Sonnet | $3.00 | $15.00 | 200K |
| Claude 3.5 Haiku | $1.00 | $5.00 | 200K |
Model compatibility
All models are accessible through the OpenAI-compatible /v1/chat/completions endpoint.
Use your existing SDKs and tools without modification.